weather

news_crawler/ollama_client.py

@@ -112,6 +112,9 @@ class OllamaClient:
                     'duration': time.time() - start_time
                 }
             
+            # Clean markdown formatting from summary
+            summary = self._clean_markdown(summary)
+            
             summary_word_count = len(summary.split())
             
             return {
@@ -303,6 +306,35 @@ German headline:
         
         return translation
     
+    def _clean_markdown(self, text):
+        """Remove markdown formatting from text"""
+        import re
+        
+        # Remove markdown headers (##, ###, etc.)
+        text = re.sub(r'^#{1,6}\s+', '', text, flags=re.MULTILINE)
+        
+        # Remove bold/italic markers (**text**, *text*, __text__, _text_)
+        text = re.sub(r'\*\*([^\*]+)\*\*', r'\1', text)
+        text = re.sub(r'__([^_]+)__', r'\1', text)
+        text = re.sub(r'\*([^\*]+)\*', r'\1', text)
+        text = re.sub(r'_([^_]+)_', r'\1', text)
+        
+        # Remove markdown links [text](url) -> text
+        text = re.sub(r'\[([^\]]+)\]\([^\)]+\)', r'\1', text)
+        
+        # Remove inline code `text`
+        text = re.sub(r'`([^`]+)`', r'\1', text)
+        
+        # Remove bullet points and list markers
+        text = re.sub(r'^\s*[-*+]\s+', '', text, flags=re.MULTILINE)
+        text = re.sub(r'^\s*\d+\.\s+', '', text, flags=re.MULTILINE)
+        
+        # Clean up extra whitespace
+        text = re.sub(r'\n\s*\n', '\n\n', text)
+        text = text.strip()
+        
+        return text
+    
     def _build_summarization_prompt(self, content, max_words):
         """Build prompt for article summarization"""
         # Truncate content if too long (keep first 5000 words)
@@ -319,6 +351,8 @@ Write in the clear, engaging, and authoritative style of New York Times Magazine
 - Focus on what matters to readers
 - Even if the source is in German or another language, write your summary entirely in English
 
+IMPORTANT: Write in plain text only. Do NOT use markdown formatting (no ##, **, *, bullets, etc.). Just write natural prose.
+
 Article:
 {content}